alpz/mech-nn
Code Repository for the paper "Mechanistic Neural Networks for Scientific Machine Learning", ICML 2024
This project helps scientists and researchers analyze complex scientific data by explicitly learning the underlying differential equations that govern dynamic systems. It takes in observational data, like measurements from physical systems or biological processes, and outputs interpretable mathematical equations that describe the system's behavior. This allows researchers to understand the 'why' behind their data, not just 'what' is happening.
No commits in the last 6 months.
Use this if you need to discover the governing equations from your scientific data, model dynamic systems with high accuracy, or enhance the interpretability of your machine learning models in scientific contexts.
Not ideal if your primary goal is to solve standard machine learning classification or regression problems without an inherent need to uncover underlying physical mechanisms.
Stars
11
Forks
1
Language
Jupyter Notebook
License
—
Category
Last pushed
Jun 04, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/alpz/mech-nn"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
NVIDIA/physicsnemo
Open-source deep-learning framework for building, training, and fine-tuning deep learning models...
SciML/NeuralPDE.jl
Physics-Informed Neural Networks (PINN) Solvers of (Partial) Differential Equations for...
NVIDIA/physicsnemo-sym
Framework providing pythonic APIs, algorithms and utilities to be used with PhysicsNeMo core to...
idrl-lab/idrlnet
IDRLnet, a Python toolbox for modeling and solving problems through Physics-Informed Neural...
mathLab/PINA
Physics-Informed Neural networks for Advanced modeling